Dontopedia

Screenshot_20260124-125729.png

From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)

Screenshot_20260124-125729.png has 122 facts recorded in Dontopedia across 67 references, with 6 live disagreements.

122 facts·11 predicates·67 sources·6 in dispute

Mostly:rdf:type(51), file name(16), filename(11)

Maturity scale raw canonical shape-checked rule-derived certified

Rdf:typein disputerdf:type

File Namein disputefileName

  • Screenshot202026-01-2620at205.25.12E280AFAM.png[7]sourceall time · 4
  • Screenshot_2025-12-02_at_9.01.00_PM.png[8]sourceall time · 468
  • Screenshot_2026-04-05_at_7.41.25_PM.png[12]sourceall time · 49
  • Screenshot_2026-03-06_at_4.18.01_PM.png[20]sourceall time · 31
  • Screenshot_2026-03-07_at_5.01.59_AM.png[22]sourceall time · 59
  • Screenshot_2026-03-07_at_8.31.14_PM.png[25]sourceall time · 91
  • Screenshot_2026-03-08_at_6.59.51_PM.png[28]sourceall time · 115
  • Screenshot_2026-03-11_at_1.32.31_AM.png[37]sourceall time · 228
  • Screenshot_2026-03-13_at_2.42.12_AM.png[38]sourceall time · 264
  • Screenshot_2026-03-14_at_8.27.21_AM.png[44]sourceall time · 305

Filenamein disputefilename

  • Screenshot_2026-01-11_at_12.36.46_AM.png[2]sourceall time · 3
  • Screenshot_2026-03-27_at_8.11.11_PM.png[9]sourceall time · 11
  • Screenshot_2026-03-07_at_10.59.49_AM.png[23]sourceall time · 66
  • Screenshot_2026-03-08_at_5.14.31_PM.png[27]sourceall time · 109
  • Screenshot_2026-03-08_at_8.25.21_PM.png[29]sourceall time · 119
  • Screenshot_2026-03-18_at_11.15.14_PM.png[48]sourceall time · 389
  • Screenshot_2026-03-19_at_2.55.14_AM.png[49]sourceall time · 408
  • Screenshot_2026-03-20_at_3.02.36_PM.png[50]sourceall time · 444
  • Screenshot_2026-04-04_at_1.24.28_PM.png[58]sourceall time · 594
  • Screenshot_2026-04-16_at_11.54.52_AM.png[62]sourceall time · 646

Inbound mentions (44)

Other subjects in dontopedia point AT this entity as a value. These are inverse relationships — e.g. "X motherOf this subject" — and answer questions the forward facts can't. Grouped by predicate.

attachedFileAttached File(11)

referencesFileReferences File(11)

hasAttachmentHas Attachment(5)

sharedFileShared File(4)

mentionsFileMentions File(2)

attachesAttaches(1)

attachesFileAttaches File(1)

commentedOnSimilarityCommented on Similarity(1)

containsAttachmentContains Attachment(1)

containsReferenceContains Reference(1)

expressesApprovalTowardsExpresses Approval Towards(1)

mentionedFileMentioned File(1)

postedImagePosted Image(1)

referencedInFileReferenced in File(1)

referencesReferences(1)

refersToEntityRefers to Entity(1)

Other facts (17)

The long tail: predicates that appear too rarely to warrant their own section. Filter or scroll to find a specific one. Each row links to its source.

17 facts
PredicateValueRef
Has FilenameScreenshot_2026-02-17_at_4.20.17_AM.png[10]
Has FilenameScreenshot_2026-02-26_at_8.34.13_PM.png[19]
Has FilenameScreenshot_2026-03-07_at_3.07.04_AM.png[21]
Has FilenameScreenshot_2026-03-09_at_8.01.18_PM.png[32]
Has FilenameScreenshot_2026-03-14_at_5.52.36_AM.png[43]
Has FilenameScreenshot_2026-03-15_at_2.09.54_PM.png[46]
Has FilenameScreenshot_2026-04-10_at_8.49.21_PM.png[59]
File Typepng[1]
File Typepng[14]
File Typepng[22]
Has File NameScreenshot_2025-03-16_at_2.38.54_PM.png[3]
Has File NameScreenshot_2026-04-21_at_11.25.02_AM.png[64]
Has File Extensionpng[6]
DepictsFlops Memory Metrics[26]
Has NameScreenshot_2026-03-10_at_12.21.44_AM.png[34]
Depicts Ci Configtrue[52]
Mime Typeimage/png[61]

Timeline

Timeline axis is valid_time — when each source says the fact was true in the world, not when Dontopedia learned about it. Retracted rows are kept for provenance; coloured stripes indicate the context kind.

labelblah/blah/10
Screenshot_from_2026-02-21_10-04-44.png
typeblah/blah/10
ex:File
fileTypeblah/blah/10
png
typeblah/design/3
ex:ImageFile
filenameblah/design/3
Screenshot_2026-01-11_at_12.36.46_AM.png
typeblah/general/2
ex:ImageFile
hasFileNameblah/general/2
Screenshot_2025-03-16_at_2.38.54_PM.png
labelblah/general/44
Screenshot_2025-05-09_at_8.15.40_AM.png
labelblah/general/75
Screenshot_2025-11-20_at_9.23.20_AM.png
typeblah/general/96
ex:FileAttachment
labelblah/general/96
Screenshot_20260124-125729.png
hasFileExtensionblah/general/96
png
typeblah/generative-tools/4
ex:File
fileNameblah/generative-tools/4
Screenshot202026-01-2620at205.25.12E280AFAM.png
fileNameblah/omega/468
Screenshot_2025-12-02_at_9.01.00_PM.png
filenameblah/papers/11
Screenshot_2026-03-27_at_8.11.11_PM.png
hasFilenameblah/random/24
Screenshot_2026-02-17_at_4.20.17_AM.png
typeblah/random/24
ex:File
typeblah/resources/10
ex:FileAttachment
typeblah/resources/49
ex:File
fileNameblah/resources/49
Screenshot_2026-04-05_at_7.41.25_PM.png
typeblah/safiersemantics/6
ex:FileAttachment
labelblah/safiersemantics/6
Screenshot_2026-01-18_at_10.53.24_PM.png
typeblah/training-and-evals/25
ex:FileAttachment
labelblah/training-and-evals/25
Screenshot_2026-02-26_at_12.58.42_AM.png
fileTypeblah/training-and-evals/25
png
labelblah/training-and-evals/32
Screenshot_from_2026-02-28_18-25-20.png
labelblah/unturf/41
Screenshot_2026-01-15_at_3.54.13_AM.png
typeblah/unturf/41
ex:File
typeblah/unturf/42
ex:File
labelblah/unturf/42
Screenshot_2026-01-17_at_2.23.25_AM.png
typeblah/unturf/66
ex:FileAttachment
labelblah/unturf/66
Screenshot_from_2026-03-09_12-35-46.png
hasFilenameblah/watt-activation/9
Screenshot_2026-02-26_at_8.34.13_PM.png
typeblah/watt-activation/31
ex:File
fileNameblah/watt-activation/31
Screenshot_2026-03-06_at_4.18.01_PM.png
typeblah/watt-activation/51
ex:File
hasFilenameblah/watt-activation/51
Screenshot_2026-03-07_at_3.07.04_AM.png
fileNameblah/watt-activation/59
Screenshot_2026-03-07_at_5.01.59_AM.png
fileTypeblah/watt-activation/59
png
filenameblah/watt-activation/66
Screenshot_2026-03-07_at_10.59.49_AM.png
typeblah/watt-activation/87
ex:File
labelblah/watt-activation/87
Screenshot_2026-03-07_at_4.58.04_PM.png
fileNameblah/watt-activation/91
Screenshot_2026-03-07_at_8.31.14_PM.png
labelblah/watt-activation/96
Screenshot_2026-03-07_at_11.12.32_PM.png
depictsblah/watt-activation/96
ex:flops-memory-metrics
filenameblah/watt-activation/109
Screenshot_2026-03-08_at_5.14.31_PM.png
typeblah/watt-activation/115
ex:File
fileNameblah/watt-activation/115
Screenshot_2026-03-08_at_6.59.51_PM.png
typeblah/watt-activation/119
ex:File
filenameblah/watt-activation/119
Screenshot_2026-03-08_at_8.25.21_PM.png
typeblah/watt-activation/137
ex:File
labelblah/watt-activation/152
Screenshot_2026-03-09_at_11.58.35_AM.png
typeblah/watt-activation/177
ex:FileAttachment
hasFilenameblah/watt-activation/177
Screenshot_2026-03-09_at_8.01.18_PM.png
typeblah/watt-activation/181
ex:ImageFile
labelblah/watt-activation/181
Screenshot_2026-03-09_at_9.53.49_PM.png
hasNameblah/watt-activation/192
Screenshot_2026-03-10_at_12.21.44_AM.png
typeblah/watt-activation/192
ex:ImageFile
labelblah/watt-activation/222
Screenshot_2026-03-11_at_1.06.16_AM.png
typeblah/watt-activation/222
ex:File
labelblah/watt-activation/226
Screenshot_2026-03-11_at_1.22.34_AM.png
fileNameblah/watt-activation/228
Screenshot_2026-03-11_at_1.32.31_AM.png
typeblah/watt-activation/264
ex:ImageFile
fileNameblah/watt-activation/264
Screenshot_2026-03-13_at_2.42.12_AM.png
typeblah/watt-activation/266
ex:File
labelblah/watt-activation/266
Screenshot_2026-03-13_at_3.17.08_AM.png
typeblah/watt-activation/269
ex:File
labelblah/watt-activation/269
Screenshot_2026-03-13_at_12.57.01_PM.png
typeblah/watt-activation/283
ex:File
labelblah/watt-activation/283
Screenshot_2026-03-13_at_7.45.57_PM.png
typeblah/watt-activation/295
ex:File
labelblah/watt-activation/295
Screenshot_2026-03-14_at_12.50.19_AM.png
hasFilenameblah/watt-activation/303
Screenshot_2026-03-14_at_5.52.36_AM.png
typeblah/watt-activation/303
ex:File
typeblah/watt-activation/305
ex:File
fileNameblah/watt-activation/305
Screenshot_2026-03-14_at_8.27.21_AM.png
typeblah/watt-activation/335
ex:ImageFile
typeblah/watt-activation/338
ex:File
hasFilenameblah/watt-activation/338
Screenshot_2026-03-15_at_2.09.54_PM.png
typeblah/watt-activation/347
ex:File
labelblah/watt-activation/347
Screenshot_2026-03-16_at_11.54.25_AM.png
filenameblah/watt-activation/389
Screenshot_2026-03-18_at_11.15.14_PM.png
typeblah/watt-activation/389
ex:ImageFile
filenameblah/watt-activation/408
Screenshot_2026-03-19_at_2.55.14_AM.png
typeblah/watt-activation/444
ex:File
filenameblah/watt-activation/444
Screenshot_2026-03-20_at_3.02.36_PM.png
typeblah/watt-activation/446
ex:File
fileNameblah/watt-activation/446
Screenshot_2026-03-20_at_7.14.30_PM.png
typeblah/watt-activation/457
ex:File
labelblah/watt-activation/457
Screenshot_2026-03-21_at_10.29.38_AM.png
depictsCiConfigblah/watt-activation/457
true
typeblah/watt-activation/473
ex:File
labelblah/watt-activation/473
Screenshot_2026-03-21_at_4.09.04_PM.png
typeblah/watt-activation/507
ex:ImageFile
fileNameblah/watt-activation/507
Screenshot_2026-03-22_at_4.29.57_PM.png
typeblah/watt-activation/535
ex:ImageFile
labelblah/watt-activation/535
Screenshot_2026-03-22_at_11.53.54_PM.png
typeblah/watt-activation/570
ex:ImageFile
labelblah/watt-activation/570
Screenshot_2026-03-25_at_3.00.27_PM.png
typeblah/watt-activation/593
ex:FileAttachment
fileNameblah/watt-activation/593
Screenshot_2026-04-04_at_1.19.21_PM.png
typeblah/watt-activation/594
ex:DigitalImage
filenameblah/watt-activation/594
Screenshot_2026-04-04_at_1.24.28_PM.png
typeblah/watt-activation/610
ex:File
hasFilenameblah/watt-activation/610
Screenshot_2026-04-10_at_8.49.21_PM.png
labelblah/watt-activation/637
Screenshot_2026-04-15_at_8.35.26_PM.png
typeblah/watt-activation/637
ex:File
fileNameblah/watt-activation/642
Screenshot_2026-04-15_at_10.09.13_PM.png
mimeTypeblah/watt-activation/642
image/png
typeblah/watt-activation/646
ex:File
filenameblah/watt-activation/646
Screenshot_2026-04-16_at_11.54.52_AM.png
typeblah/watt-activation/667
ex:File
fileNameblah/watt-activation/667
Screenshot_2026-04-20_at_1.31.56_AM.png
typeblah/watt-activation/670
ex:ImageFile
hasFileNameblah/watt-activation/670
Screenshot_2026-04-21_at_11.25.02_AM.png
typeblah/watt-activation/683
ex:File
filenameblah/watt-activation/683
Screenshot_2026-04-23_at_1.37.01_PM.png
typeblah/watt-activation/701
ex:ImageFile
labelblah/watt-activation/701
Screenshot_2026-05-01_at_2.19.37_PM.png
typeblah/watt-activation/707
ex:ImageFile
fileNameblah/watt-activation/707
Screenshot_2026-05-01_at_8.28.27_PM.png

References (67)

67 references
  1. [1]103 facts
    ctx:discord/blah/blah/10
    • full textblah-10
      text/plain2 KBdoc:agent/blah-10/18fc4a9a-f597-46e7-bea7-52f85a1d90be
      Show excerpt
      [2026-02-21 13:57] foxhop.: making a cancel run button [2026-02-21 13:57] foxhop.: already have it sped up i wanna try with without contention [2026-02-21 14:23] foxhop.: Vercel – blah.dev - Git author russellballestrini must have access to
  2. [2]32 facts
    ctx:discord/blah/design/3
    • full textdesign-3
      text/plain3 KBdoc:agent/design-3/8c34c4f3-77a1-4826-81ef-a2aced492951
      Show excerpt
      [2026-01-10 11:22] salvador_james: I’m working on my design skills here boys would be nice to get some ideas from you guys [2026-01-10 11:22] salvador_james: https://www.jamesspalding.org/design [2026-01-10 11:23] salvador_james: Basically
  3. [3]22 facts
    ctx:discord/blah/general/2
    • full textgeneral-2
      text/plain3 KBdoc:agent/general-2/1847a6c7-5002-49f6-84be-549076356dd3
      Show excerpt
      [2025-03-15 01:04] ajaxdavis: if you want to try generate the dynamic tools (might break everything, may not) `blah-mcp-test run --prompt "create a tool that says why typescript sucks but in the spirit of the users favorite movie"` [2025-
  4. [4]441 fact
    ctx:discord/blah/general/44
    • full textgeneral-44
      text/plain3 KBdoc:agent/general-44/1494eef8-ea9e-4870-a158-2517ef364366
      Show excerpt
      [2025-05-06 11:15] ajaxdavis: https://github.com/thomasdavis/breakbreakdown this is the progress i've made on my deep research alternative. still just working on analyzing intent [2025-05-06 11:18] ajaxdavis: takes a question "how gay is au
  5. [5]751 fact
    ctx:discord/blah/general/75
    • full textgeneral-75
      text/plain3 KBdoc:agent/general-75/18b5089d-9ba0-4e64-9633-92e4a2d63b6e
      Show excerpt
      [2025-11-17 19:19] jonathanestes.99: Hi all! I’m a senior full-stack blockchain engineer with 7 years of experience building production-grade smart contracts, scaling backend infrastructure, and delivering polished frontend dApps. My work s
  6. [6]963 facts
    ctx:discord/blah/general/96
    • full textgeneral-96
      text/plain2 KBdoc:agent/general-96/34a01c4b-b58b-4183-a19c-588686a2621f
      Show excerpt
      [2026-01-24 02:52] traves_theberge: 😂 [2026-01-24 02:54] traves_theberge: I want age of empire + Pokemon + RS world to build in [2026-01-24 02:55] ajaxdavis: Lol at the air level assign your villagers to cut wood, but then you gotta go into
  7. [7]42 facts
    ctx:discord/blah/generative-tools/4
    • full textgenerative-tools-4
      text/plain3 KBdoc:agent/generative-tools-4/ddafd324-353d-42cf-9bce-e8e39173e4bf
      Show excerpt
      [2026-01-25 17:32] traves_theberge: ┌──────────────────────────┐ │ Real Data │ │ (DB rows, APIs, events) │ └────────────┬─────────────┘ │
  8. [8]4681 fact
    ctx:discord/blah/omega/468
    • full textomega-468
      text/plain3 KBdoc:agent/omega-468/5818af60-1832-49bf-999b-c598f0337715
      Show excerpt
      [2025-12-02 10:46] omega [bot]: <@1340709301794373632> foxhop. asks you now for a Ruby "Hello World" program that uses random repetition from 1 to 9 times for the printed message. Please provide this via direct message. [2025-12-02 10:46] u
  9. [9]111 fact
    ctx:discord/blah/papers/11
    • full textpapers-11
      text/plain3 KBdoc:agent/papers-11/87075ea2-dc33-49a1-bae8-a27e43f3b456
      Show excerpt
      [2026-03-27 04:29] rolandnsharp7643: <@1211062099137265723> does this mean anything to you?: Have you tried second-order dynamics? Your γ-cumsum is first-order — decays but doesn't ring. Our transfer function is second-order — it oscillate
  10. [10]242 facts
    ctx:discord/blah/random/24
    • full textrandom-24
      text/plain3 KBdoc:agent/random-24/c8401fc9-2a91-4ebc-833d-8d389b917d0e
      Show excerpt
      [2026-02-17 05:08] xenonfun: well I'm at minutes now, so I got better output ``` Batch size: 64 Learning rate: 0.00003 → 0.000003 Iter 830 | Loss: 2.4261 | Val: 2.4313 (ppl 11.4) | LR: 0.000013 | Best: 2.3954 @821 | 1802ms/iter | 271s ela
  11. [11]101 fact
    ctx:discord/blah/resources/10
    • full textresources-10
      text/plain3 KBdoc:agent/resources-10/f39a62f9-2ad8-4dfd-99cf-e1068d4c2134
      Show excerpt
      [2025-07-01 04:45] ajaxdavis: https://www.philschmid.de/context-engineering [2025-07-01 20:16] ajaxdavis: https://simedw.com/2025/06/23/introducing-spegel/ <@329116693186215938> [2025-07-01 20:17] foxhop.: Fuck that's coo [2025-07-01 21:35]
  12. [12]492 facts
    ctx:discord/blah/resources/49
    • full textresources-49
      text/plain3 KBdoc:agent/resources-49/65049462-7ef3-449f-b842-ba6dcf42c1bf
      Show excerpt
      [2026-04-05 20:44] xenonfun: `blossom-rs` embeddable server library coming next, as nobody has build it for some reason, thre is a nice server but forced MySql and no lib bindings, I had a barebones version so monster merging will be next p
  13. [13]62 facts
    ctx:discord/blah/safiersemantics/6
    • full textsafiersemantics-6
      text/plain2 KBdoc:agent/safiersemantics-6/da7fe9a5-ae2a-49fe-8ef6-b3cce30eeab0
      Show excerpt
      [2026-01-19 03:52] SafierSemantics [bot]: hey fuckers! [2026-01-19 03:53] xenonfun: well took all day but I'm satified. (files: Screenshot_2026-01-18_at_10.53.24_PM.png) [2026-01-19 03:54] ajaxdavis: lmao beautiful [2026-01-19 03:54] ajaxda
  14. [14]253 facts
    ctx:discord/blah/training-and-evals/25
    • full texttraining-and-evals-25
      text/plain2 KBdoc:agent/training-and-evals-25/e24e7b5b-4c3d-43fe-b0a2-7c1baa240994
      Show excerpt
      [2026-02-25 14:57] omega [bot]: **New: 3D Radial Training Visualization (Three.js)** Added an interactive 3D scene to the run detail page below the oscillation chart. Concentric rings map training metrics radially around the timeline: - *
  15. [15]321 fact
    ctx:discord/blah/training-and-evals/32
    • full texttraining-and-evals-32
      text/plain2 KBdoc:agent/training-and-evals-32/ab593bf1-698c-4792-b6ac-21d15440d8eb
      Show excerpt
      [2026-02-28 15:19] ajaxdavis: (files: message.txt) [2026-02-28 23:17] foxhop.: https://microgpt.ai.unturf.com/v1/models [2026-02-28 23:18] foxhop.: (files: message.txt) [2026-02-28 23:19] foxhop.: look at dem JSON boyos & girlie [2026-02-
  16. [16]412 facts
    ctx:discord/blah/unturf/41
    • full textunturf-41
      text/plain3 KBdoc:agent/unturf-41/a1c1a382-f3b8-4d18-98f5-e90cd2219286
      Show excerpt
      [2026-01-14 11:26] foxhop.: sounds horrible wihtout claudes help. [2026-01-14 11:26] foxhop.: lmao [2026-01-14 11:26] lisamegawatts: i keep looking at projects for dynamic routing, use smart model for smart things [2026-01-14 11:27] ajaxdav
  17. [17]422 facts
    ctx:discord/blah/unturf/42
    • full textunturf-42
      text/plain2 KBdoc:agent/unturf-42/f1ad4aa3-91dd-4389-b4c8-8736011ee497
      Show excerpt
      [2026-01-15 17:01] foxhop.: Ok I'm pushing to main not that i expect you to watch but I'm factoring out old stylesheets now. [2026-01-15 17:02] foxhop.: at the moment I'm just trying to move every page over. (except admin that will stay ret
  18. [18]662 facts
    ctx:discord/blah/unturf/66
    • full textunturf-66
      text/plain3 KBdoc:agent/unturf-66/a648f108-3ad2-4d09-876d-bd2bc4597276
      Show excerpt
      [2026-03-09 15:50] omega [bot]: 🔧 2/2: createBlogPost ✅ Success **Args:** ```json { "title": "Exploring the Six Roads to C.U.N.T: A Detailed White Paper with Diagrams", "content": "This blog post explores the \"Six Roads to C.U.N.T\" co
  19. [19]91 fact
    ctx:discord/blah/watt-activation/9
    • full textwatt-activation-9
      text/plain3 KBdoc:agent/watt-activation-9/b3eaeadb-4d30-449a-926d-ac2cf3ed101d
      Show excerpt
      [2026-02-27 01:34] xenonfun: (files: Screenshot_2026-02-26_at_8.34.13_PM.png) [2026-02-27 02:10] xenonfun: ``` +**Conclusion**: The phase-gated no-FFN architecture is the correct design. The mixer should be the sole sequence+channel mixing
  20. [20]312 facts
    ctx:discord/blah/watt-activation/31
    • full textwatt-activation-31
      text/plain3 KBdoc:agent/watt-activation-31/46160fba-f33d-4eec-8b0a-faef1e38bef4
      Show excerpt
      [2026-03-06 21:22] xenonfun: Vocab 8K expansion trial. much slower ` 17.1 it/s (4.4K tok/s | 0.80%)` Training is live and healthy. Here's the status: v8k training — iter 4500 / 100000 (4.5%) - Speed: 17.3 it/s, ~92 min remaining - Lo
  21. [21]512 facts
    ctx:discord/blah/watt-activation/51
    • full textwatt-activation-51
      text/plain3 KBdoc:agent/watt-activation-51/53cd7634-6f49-4bb0-9083-629d07a48d10
      Show excerpt
      [2026-03-07 07:59] xenonfun: ``` Full results are in. Here's the complete picture: ┌───────────────────┬───────────┬──────────┬──────┬──────────┬──────┐ │ Config │ Final PPL │ Best PPL │ r │ Clusters │ it/s │ ├─────────
  22. [22]592 facts
    ctx:discord/blah/watt-activation/59
    • full textwatt-activation-59
      text/plain3 KBdoc:agent/watt-activation-59/8ec6d45a-655b-465a-adad-bb94f460445f
      Show excerpt
      [2026-03-07 09:46] xenonfun: 618K non-ASCII chars, dominated by smart quotes (464K) and fancy dashes (77K). These each become 3-byte sequences that the BPE tokenizer splits into individual byte tokens — wasting capacity on âĢľ garbage. L
  23. [23]661 fact
    ctx:discord/blah/watt-activation/66
    • full textwatt-activation-66
      text/plain2 KBdoc:agent/watt-activation-66/b8a9d69a-c3a7-4d63-a909-00e2fb3be556
      Show excerpt
      [2026-03-07 15:56] lisamegawatts: there might be a way to use it for rope but we didn't find the right model [2026-03-07 15:57] lisamegawatts: it does embed positioning space, we may be looking in wrong location though [2026-03-07 15:57] xe
  24. [24]872 facts
    ctx:discord/blah/watt-activation/87
    • full textwatt-activation-87
      text/plain2 KBdoc:agent/watt-activation-87/21549fe5-2355-4b51-9d7e-42d9fb1af8c0
      Show excerpt
      [2026-03-07 21:54] xenonfun: ``` iter 8000/10000 | loss=4.2647 | PPL=71.1 | lr=6.16e-05 | 2.2 it/s (9.1K tok/s) | mem=1848MB peak=20665MB Saved checkpoint: ./akan_gpt2_checkpoints/checkpoint_iter_8000.npz iter 8500/10000 | loss=4.2438
  25. [25]911 fact
    ctx:discord/blah/watt-activation/91
    • full textwatt-activation-91
      text/plain3 KBdoc:agent/watt-activation-91/61aeb5f1-b837-4123-a6c4-b76d719d0b25
      Show excerpt
      [2026-03-08 00:46] xenonfun: ``` Looks good. Now let me calculate the exact iterations and launch: - 133M tokens / 4096 = 32,471 iters per epoch - 2 epochs = 64,942 total iters - Already done: 10,000 - Remaining: 54,942 iters (rou
  26. [26]962 facts
    ctx:discord/blah/watt-activation/96
    • full textwatt-activation-96
      text/plain3 KBdoc:agent/watt-activation-96/1496da73-efd0-4eb3-9ee4-4a522042ca36
      Show excerpt
      [2026-03-08 04:10] xenonfun: ``` How It Fits the Plan The symbiogenesis library has already done the heavy lifting for Phases 1–2. Here's how each piece maps: Plan Phase symbiogenesis component Status Phase 0: WS baseline Rotation
  27. [27]1091 fact
    ctx:discord/blah/watt-activation/109
    • full textwatt-activation-109
      text/plain3 KBdoc:agent/watt-activation-109/4ebcaf29-8e8c-435b-91fc-5790f13dba4d
      Show excerpt
      [2026-03-08 21:13] xenonfun: ``` ⏺ All done. Here's the full summary of what the review found and fixed: Critical fixes: - _dtype_eps inconsistency — standardized all calls to use q_feat.dtype (not x.dtype) so forward/step match - Re
  28. [28]1152 facts
    ctx:discord/blah/watt-activation/115
    • full textwatt-activation-115
      text/plain3 KBdoc:agent/watt-activation-115/105443fa-23c3-42fc-a3a6-065e0c10a484
      Show excerpt
      [2026-03-08 22:44] xenonfun: ``` === grouped1 (seq=2048) === Training HarmonicGPT | attn=grouped1 d=768 L=12 H=12 seq=2048 Parameters: 86,825,760 Loaded 5,000 train sequences of length 2048 iter 10/100 | loss 5.4746 | lr 3.00e-04 | tok/
  29. [29]1192 facts
    ctx:discord/blah/watt-activation/119
    • full textwatt-activation-119
      text/plain3 KBdoc:agent/watt-activation-119/dd015076-4b38-4017-9483-3f91bdce858d
      Show excerpt
      [2026-03-09 00:25] xenonfun: okay at least generating something probablt still some bugs. ⏺ Committed and pushed. Key things done this session: 1. docs/symbiogenesis.md saved as a core document, linked prominently from CLAUDE.md 2. Roo
  30. [30]1371 fact
    ctx:discord/blah/watt-activation/137
    • full textwatt-activation-137
      text/plain2 KBdoc:agent/watt-activation-137/9608fbdb-8ce7-4e5b-ac20-5c329d46eade
      Show excerpt
      [2026-03-09 06:07] xenonfun: ``` ❯ are you sure this is principaled? ⏺ No, you're right to push back. L1 normalization is ad-hoc — it bounds the magnitude but it's not derived from the manifold. The principled fix is to normalize the mean
  31. [31]1521 fact
    ctx:discord/blah/watt-activation/152
    • full textwatt-activation-152
      text/plain2 KBdoc:agent/watt-activation-152/ab95bd3d-0565-48ac-811e-d48a48d1114c
      Show excerpt
      [2026-03-09 15:56] xenonfun: ``` Prompt: 'How many people are in the unitied states around 1950?' temp=0.8 top_k=40 stop=<|endoftext|> (100257) ──────────────────────────────────────────────────────────── How many people are in the uniti
  32. [32]1772 facts
    ctx:discord/blah/watt-activation/177
    • full textwatt-activation-177
      text/plain2 KBdoc:agent/watt-activation-177/1848e53e-9103-4e36-aa1e-3412420c8756
      Show excerpt
      [2026-03-09 23:15] xenonfun: ``` ⏺ Results are poor — actually worse than LoRA r16 (val ppl 287 vs 236). The core problem is becoming clear: it's the dataset quality, not the training method. NQ has multiple valid answers joined with " /
  33. [33]1812 facts
    ctx:discord/blah/watt-activation/181
    • full textwatt-activation-181
      text/plain3 KBdoc:agent/watt-activation-181/a38e89b1-8c19-4e64-aa47-644f1d1e399d
      Show excerpt
      [2026-03-10 01:48] xenonfun: ``` Performance hit ┌────────────────────────────────────────────────┬────────────────────────────────┐ │ Step │ Cost │ ├─────────────
  34. [34]1922 facts
    ctx:discord/blah/watt-activation/192
    • full textwatt-activation-192
      text/plain3 KBdoc:agent/watt-activation-192/c3ca4e62-2524-47f4-9e3e-6cb28f08f78c
      Show excerpt
      [2026-03-10 04:10] xenonfun: ⏺ Working correctly now. Full comparison: ```┌──────────────────────┬────────────────────┬─────────────────────────┐ │ │ RotAdamW fine-tune │ LoheOptimizer fine-tune │ ├─────────────────
  35. [35]2222 facts
    ctx:discord/blah/watt-activation/222
    • full textwatt-activation-222
      text/plain3 KBdoc:agent/watt-activation-222/d8201f0f-b5d1-4b50-9f4e-2aca2c0d4c1e
      Show excerpt
      [2026-03-11 05:02] xenonfun: ⏺ mx.compile with RotationalAdamW is a dead end — the optimizer creates new array objects on each step, so inputs=[model.state] captures stale references. The error "array without primitive" is exactly what CL
  36. [36]2261 fact
    ctx:discord/blah/watt-activation/226
    • full textwatt-activation-226
      text/plain2 KBdoc:agent/watt-activation-226/2cdeaf5e-92ba-4f5c-855d-1846c41ec9d5
      Show excerpt
      [2026-03-11 05:18] xenonfun: ⏺ The inter-layer graph confirms the designer's insight exactly: No edges above 0.5 — every block is nearly orthogonal to every other block. Mean cosine similarity across all layer distances is noise (±0.08
  37. [37]2281 fact
    ctx:discord/blah/watt-activation/228
    • full textwatt-activation-228
      text/plain3 KBdoc:agent/watt-activation-228/218c4ece-61aa-47aa-a16e-b77f7f994d5f
      Show excerpt
      [2026-03-11 05:23] xenonfun: ⏺ It is, and the math backs it up cleanly. What the network discovered spontaneously is essentially a depth-wise DFT — the same decomposition that LoheFFNv3 uses within each block (ring → DFT modes), but now o
  38. [38]2642 facts
    ctx:discord/blah/watt-activation/264
    • full textwatt-activation-264
      text/plain2 KBdoc:agent/watt-activation-264/555cd9a1-321c-4f18-8f17-7bef422894a1
      Show excerpt
      [2026-03-13 05:30] xenonfun: ``` I wrote the full plan in docs/claude/plans/tokenizerless_phase_stream_plan.md. Core recommendation from the plan: - do not do pure one-byte-per-step modeling first - build a tokenizerless byte_patch
  39. [39]2662 facts
    ctx:discord/blah/watt-activation/266
    • full textwatt-activation-266
      text/plain2 KBdoc:agent/watt-activation-266/0dd3318c-38a8-4ab0-8b7a-743748e72c54
      Show excerpt
      [2026-03-13 07:20] xenonfun: • Ran it. Long-prompt test (context_patches=128000, prompt = 1,024,000 bytes, generated 64 patches, compiled cached decode): - prompt bytes: 1,024,000 - generated patches: 64 - total elapsed: 231.8s
  40. [40]2692 facts
    ctx:discord/blah/watt-activation/269
    • full textwatt-activation-269
      text/plain2 KBdoc:agent/watt-activation-269/28541c3c-993b-46f3-bb42-9a8d45d63f59
      Show excerpt
      [2026-03-13 16:50] xenonfun: ⏺ Best val_loss: 0.299 — broke below 0.310 (previous best from diffusion_norm) and still falling at step 5000. New record. ``` ┌────────────────────────────────┬───────┬──────────┬─────────┐ │
  41. [41]2832 facts
    ctx:discord/blah/watt-activation/283
    • full textwatt-activation-283
      text/plain2 KBdoc:agent/watt-activation-283/512b04b9-3f20-475b-ab8c-3e08540bd727
      Show excerpt
      [2026-03-13 23:44] xenonfun: ``` ⏺ Baseline Comparison ┌─────────────────────────┬────────────┬────────────┐ │ Mode │ Final Loss │ Throughput │ ├─────────────────────────┼────────────┼────────────┤ │ No VQ
  42. [42]2952 facts
    ctx:discord/blah/watt-activation/295
    • full textwatt-activation-295
      text/plain3 KBdoc:agent/watt-activation-295/3934680b-d58b-4c73-8470-2c337c1a045e
      Show excerpt
      [2026-03-14 04:39] xenonfun: ```❯ ⏺ Now I have the full picture. Here's my MLX performance review: Spherical VQ — MLX Performance Review Good patterns: 1. _l2_normalize uses + eps inside sqrt (line 38) — matches lohe_normalize sema
  43. [43]3032 facts
    ctx:discord/blah/watt-activation/303
    • full textwatt-activation-303
      text/plain3 KBdoc:agent/watt-activation-303/f92363d0-718f-4ef6-a9b7-9ca9251c0dc7
      Show excerpt
      [2026-03-14 08:52] xenonfun: ⏺ Subagent working on: 1. Symbol emergence marker — vertical dashed gold line on all charts 2. Coupling sweep comparison table — auto-detect K= runs, show summary 3. Scatter plot — global_r vs code_separat
  44. [44]3052 facts
    ctx:discord/blah/watt-activation/305
    • full textwatt-activation-305
      text/plain3 KBdoc:agent/watt-activation-305/4309ac1d-dc27-4020-9ee7-50e427dd436e
      Show excerpt
      [2026-03-14 12:17] lisamegawatts: well we still crushing neat, but apparently that under compute matched baseline so we going to do yet another 5 seed for conclusive apples to apples neat vs symbio at NAS [2026-03-14 12:27] xenonfun: (file
  45. [45]3351 fact
    ctx:discord/blah/watt-activation/335
    • full textwatt-activation-335
      text/plain2 KBdoc:agent/watt-activation-335/dd79a73c-09f4-4ca4-992c-61e51914a192
      Show excerpt
      [2026-03-15 14:31] xenonfun: ⏺ 8.40M params — essentially the same as the lohe_spherical run (8.45M). Same model size, same data shape, but lohe_complex + SEQ=256 reached ppl=6.1 in 855 steps vs 40,000 steps. That's a ~47× faster converg
  46. [46]3382 facts
    ctx:discord/blah/watt-activation/338
    • full textwatt-activation-338
      text/plain3 KBdoc:agent/watt-activation-338/5291b646-c08b-45ca-b1fe-b63fc86c3354
      Show excerpt
      [2026-03-15 16:56] xenonfun: ``` ⏺ No — LoheSphericalComplexAttention added complex gates (bandpass resonators) and complex coupling (phase-shifted sync). But the Lohe sync itself still normalizes to S^{H-1}: Q = lohe_normalize(self.proj
  47. [47]3472 facts
    ctx:discord/blah/watt-activation/347
    • full textwatt-activation-347
      text/plain2 KBdoc:agent/watt-activation-347/f5c35cb2-4a8a-467c-ac77-0754bba63d48
      Show excerpt
      [2026-03-16 15:40] xenonfun: trying to get dynamics we wanted from start to really work, fact is its been doing very well and most of signal has been getting smashed. finally free of normalization in layers, that is where our amplitude sign
  48. [48]3892 facts
    ctx:discord/blah/watt-activation/389
    • full textwatt-activation-389
      text/plain3 KBdoc:agent/watt-activation-389/d281c6e7-74c2-4566-8196-67523bbf6685
      Show excerpt
      [2026-03-19 03:05] xenonfun: ⏺ BPB 5.20 for L=2 — worse than before (was 4.15). The new custom encoding is worse than OFDM for G=8 H=4. The OFDM table had carefully designed quaternion states; the new table just uses identity/i vectors. L=6
  49. [49]4081 fact
    ctx:discord/blah/watt-activation/408
    • full textwatt-activation-408
      text/plain2 KBdoc:agent/watt-activation-408/5084227c-09bf-490d-affa-7c62f4061de3
      Show excerpt
      [2026-03-19 06:38] xenonfun: ⏺ Yes — the same way we did decay gates. The coupling strength should be derived from the oscillator state, not fixed: Principled approach: coupling = f(coherence between the two groups being coupled). Groups
  50. [50]4442 facts
    ctx:discord/blah/watt-activation/444
    • full textwatt-activation-444
      text/plain2 KBdoc:agent/watt-activation-444/885ad207-9977-4a41-b00d-589966869135
      Show excerpt
      [2026-03-20 17:49] xenonfun: <@1211062099137265723>, had it reread your FedSym merge, think this is closer to what you desribed and has zero scaling issues. ``` ⏺ Now I see it. The key things I missed: 1. _transfer_weights_parallel with
  51. [51]4462 facts
    ctx:discord/blah/watt-activation/446
    • full textwatt-activation-446
      text/plain3 KBdoc:agent/watt-activation-446/f0ca57f6-5ee0-47fe-be17-374fd38df4fd
      Show excerpt
      [2026-03-20 21:08] xenonfun: ``` The impact ranking from today: 1. Phase coupling (DYN-H4): 2.103 → 2.096 BPB, +1.5dB SNR, +33% capacity — biggest win 2. seq=128 (match receptive field): ~2.1 → ~1.9 BPB — huge, but config not archite
  52. [52]4573 facts
    ctx:discord/blah/watt-activation/457
    • full textwatt-activation-457
      text/plain2 KBdoc:agent/watt-activation-457/2e8b03b4-3b3a-4823-b2c8-a92329812095
      Show excerpt
      [2026-03-21 13:42] xenonfun: ``` ⏺ Clear answer at step 1000: ┌─────────────────┬───────────────┬─────────┬──────────┐ │ Optimizer │ Step 1000 BPB │ SNR │ Capacity │ ├─────────────────┼───────────────┼─────────┼──────────┤
  53. [53]4732 facts
    ctx:discord/blah/watt-activation/473
    • full textwatt-activation-473
      text/plain2 KBdoc:agent/watt-activation-473/bbee128e-eb0e-43a7-904e-88cd885d13dd
      Show excerpt
      [2026-03-21 19:47] xenonfun: ``` ⏺ Both done. Side-by-side comparison: ┌──────────┬─────────────┬────────────┐ │ │ Finite-diff │ Analytical │ ├──────────┼─────────────┼────────────┤ │ Best BPB │ 2.04 │ 2.19 │
  54. [54]5072 facts
    ctx:discord/blah/watt-activation/507
    • full textwatt-activation-507
      text/plain2 KBdoc:agent/watt-activation-507/6467e4af-ad80-4862-85f3-685e0bc8547e
      Show excerpt
      [2026-03-22 20:26] xenonfun: ⏺ 917 tests pass (the rebase picked up one more test from the CHON commits that landed on master). All done. Here's what was done: Documentation updates: - docs/portal.html — Clifford/Gauge sidebar expan
  55. [55]5352 facts
    ctx:discord/blah/watt-activation/535
    • full textwatt-activation-535
      text/plain3 KBdoc:agent/watt-activation-535/daba214f-a48a-449c-92f2-fe80bcf027e0
      Show excerpt
      [2026-03-23 03:50] xenonfun: ``` ├─────────────────────────────────────────┼────────────────────────────────────────────────────┤ │ harmonic-core/src/cuda_backend.rs │ New — CudaContext with same API surface as │ │
  56. [56]5702 facts
    ctx:discord/blah/watt-activation/570
    • full textwatt-activation-570
      text/plain3 KBdoc:agent/watt-activation-570/dde247dc-60cd-43c8-b5c7-8df30312afe8
      Show excerpt
      [2026-03-25 18:45] xenonfun: ⏺ Pushed. Here's what UniversalAlgebra.lean establishes — the dimension-independence argument: universal_sync_mechanism proves for arbitrary CliffordAlgebra Q (any quadratic form Q, any module M, any dimens
  57. [57]5932 facts
    ctx:discord/blah/watt-activation/593
    • full textwatt-activation-593
      text/plain3 KBdoc:agent/watt-activation-593/5c383b0f-5e7c-4f28-b8e6-6c00caa3ef98
      Show excerpt
      [2026-04-04 17:10] xenonfun: ⏺ Tiled is a massive win. Now let me wire it into the production code and commit. ``` ┌────────┬─────────────┬─────────────┬─────────────┐ │ N │ Fused f32 │ Tiled f32 │ Improvement │ ├────────┼───
  58. [58]5942 facts
    ctx:discord/blah/watt-activation/594
    • full textwatt-activation-594
      text/plain3 KBdoc:agent/watt-activation-594/d9974ad5-bce6-44fb-a387-861b63507258
      Show excerpt
      [2026-04-04 17:21] xenonfun: ``` The headline numbers ┌──────────────────────┬─────────────────┬───────────────┬─────────┐ │ │ Scalar (before) │ Par tiled AMX │ Speedup │ ├──────────────────────┼───────────────
  59. [59]6102 facts
    ctx:discord/blah/watt-activation/610
    • full textwatt-activation-610
      text/plain2 KBdoc:agent/watt-activation-610/b212896a-b928-4ffe-a8bc-59a715e4bb50
      Show excerpt
      [2026-04-11 00:14] xenonfun: Its fixed its Iroh race bugs onto the cool shit: Writing comprehensive integration test… (7m 7s · ↓ 11.9k tokens · thought for 11s) ⎿  ◼ Write LEARN_GNOSTR_CLOUD end-to-end integration test [2026-04-11 00:49]
  60. [60]6372 facts
    ctx:discord/blah/watt-activation/637
    • full textwatt-activation-637
      text/plain3 KBdoc:agent/watt-activation-637/19b1b41c-2a51-4202-8887-489a5512853c
      Show excerpt
      [2026-04-16 00:35] xenonfun: Proposed new order 1. Batching fix for training path (quick) — apply the same batched_linear_forward change to forward_train and its backward. Free 2.5× on training throughput. This must happen before Optio
  61. [61]6422 facts
    ctx:discord/blah/watt-activation/642
    • full textwatt-activation-642
      text/plain3 KBdoc:agent/watt-activation-642/3d74a9d0-e733-41fb-ac2c-53a6f761291f
      Show excerpt
      [2026-04-16 02:04] xenonfun: ``` BPB 8.37 → 2.35 in 1,800 steps. Clean convergence, no instability. The first checkpoint at step 2,000 is about to save. Throughput steady at ~7.2K tok/s at batch=16 with Option B + RotationalAdamW. For
  62. [62]6462 facts
    ctx:discord/blah/watt-activation/646
    • full textwatt-activation-646
      text/plain2 KBdoc:agent/watt-activation-646/84b51c92-144f-432e-8454-c9f4c46ef821
      Show excerpt
      [2026-04-16 03:27] xenonfun: ``` ⏺ Step 1,200: BPB 2.90 best, ~1,899 tok/s. Training well — BPB 8.6 → 2.9 in 1.2K steps. Throughput dipped slightly at step 1000 due to the DoReMi reference snapshot (cloning 50M params to disk + loading)
  63. [63]6672 facts
    ctx:discord/blah/watt-activation/667
  64. [64]6702 facts
    ctx:discord/blah/watt-activation/670
    • full textwatt-activation-670
      text/plain3 KBdoc:agent/watt-activation-670/d9fd63e9-d1a4-4d2d-9849-fcaa1f434b61
      Show excerpt
      [2026-04-20 17:11] xenonfun: Important observations: 1. Neither feedback variant is catastrophically diverging at peak LR 3e-3. The model produces grammatically-shaped output; the damage is only at the vocabulary level, not structural.
  65. [65]6832 facts
    ctx:discord/blah/watt-activation/683
    • full textwatt-activation-683
      text/plain3 KBdoc:agent/watt-activation-683/1d89c3e1-d173-4432-968b-898b740f9ed3
      Show excerpt
      [2026-04-23 17:37] xenonfun: All 20 layers healthy — no issues. - Zero dead layers. Contribution ratio range: 34-157% (dead threshold is <1%). L0 dominates (157%) as expected input-conditioner; L1-L19 all 34-94%. - No gate collapse. α
  66. [66]7012 facts
    ctx:discord/blah/watt-activation/701
    • full textwatt-activation-701
      text/plain2 KBdoc:agent/watt-activation-701/4ee5b525-67f9-428d-a8b0-5740541ea993
      Show excerpt
      [2026-05-01 18:00] xenonfun: Confirmed: _dedup.sqlite is CREATE TABLE seen (checksum TEXT PRIMARY KEY) with 4.7 million checksums. So it is useful for provenance/dedup integrity, but the actual training text and curriculum metadata are in t
  67. [67]7072 facts
    ctx:discord/blah/watt-activation/707
    • full textwatt-activation-707
      text/plain1 KBdoc:agent/watt-activation-707/7e5b0709-a624-43e0-ba23-577500b9040c
      Show excerpt
      [2026-05-02 00:07] xenonfun: Current `best.pt` is still the rolling best at **step 180**, loss **0.8153**, BPB **1.1762**. Prompt: `Jack and Jill went up the hill to get a drink of water.` Temp `0.7`, top-k `50`, 1K bytes: ```text "We d

See also

Keep researching

Missing something or suspicious of what's here? Kick off a research session — a Claude agent will investigate, cite its sources, and file new facts into a dedicated context you can review before accepting into the shared view.